SiriusBI: Building End-to-End Business Intelligence Enhanced by Large Language Models

2024-11-09

arXiv.org

AI Summary

Contemporary BI systems face three critical challenges in the LLM era: legacy functionalities inadequately support dynamic analytical requirements; single-turn SQL generation impedes iterative, clarifying multi-turn interactions; and cross-domain adaptation incurs prohibitively high customization costs. To address these, we propose SiriusBI—the first end-to-end, LLM-augmented BI system designed for industrial deployment. It introduces an application-oriented multi-turn dialogue query module, a dual-path SQL generation mechanism balancing accuracy and deployment efficiency, and a full-stack BI orchestration engine spanning data preparation, analysis, and visualization. Built on a cloud-native microservice architecture, SiriusBI has been deployed across Tencent’s financial, advertising, and cloud business units, achieving SQL accuracy rates of 97%, 89%, and 91%, respectively. As a standalone cloud service, it supports dozens of external enterprises, demonstrating industrial-grade practicality, robustness, and scalability.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The rapid advancement of AI technologies, particularly Large Language Models (LLMs), is establishing a new paradigm for Business Intelligence (BI). Despite the emergence of pioneering work in enhancing BI systems with LLMs, we have identified the following three issues when deployed in real industrial scenarios: interaction limitations, performance bottlenecks, and functionality deficiencies. In this paper, we present SiriusBI, an end-to-end business intelligence system that is designed to address the three issues simultaneously. First, we propose an intelligent and application-oriented module called multi-round dialogue with querying, which aims to overcome the prevalent interaction limitations in current BI solutions. Next, to mitigate the performance bottlenecks caused by scenario migration, we introduce two SQL generation methods that strike a balance between accuracy and deployment costs. Finally, to tackle the practical challenges posed by functionality deficiencies, we develop an end-to-end workflow that covers the entire BI process, ensuring that SiriusBI delivers a robust and complete set of functionalities. As an independent cloud service in Tencent's data platform, SiriusBI has been applied across Tencent's finance, advertising, and cloud sectors, providing services to dozens of enterprise clients. Experiments on real-world datasets and practical applications in industrial BI scenarios demonstrate the practicality and effectiveness of SiriusBI. Remarkably, SiriusBI achieves remarkable accuracy rates of 97% in SQL generation for Tencent Finance, 89% for Tencent Advertisement, and 91% for Tencent Cloud.

Problem

• Legacy BI systems lack functionality for LLM-era demands
• Single-round SQL generation fails in multi-round clarification
• High costs hinder cross-domain adaptation in BI solutions

Innovation

• End-to-end architecture with multi-module coordination
• Multi-round dialogue for SQL generation clarification
• Data-conditioned SQL generation method selection strategy